We present Network Polygraph (https://polygraph.io), a network monitoring service based on NetFlow/IPFIX that benefits from more than 10 years of research in the fields of network monitoring and traffic classification at UPC BarcelonaTech. The main novelty of this tool is that it can be deployed as a service, either on premises or in the cloud, which makes it much easier and cheaper to deploy, while still obtaining classification accuracies similar to those tools based on DPI. Network Polygraph’s technology also solves the limitations of previous machine learning based algorithms proposed by the research community, by integrating an unique, fully-automatic retraining system that allows the system to retrain itself, without human interventio...
The main objective of the thesis is the development of a new software package for plotting of the ne...
Accurate per-application network traffic characterization is becoming in-creasingly difficult in the...
International audienceNowadays, Machine Learning (ML) tools are commonly used in every area of scien...
In order for businesses to maintain their productivity today, it iscrucial that they constantly moni...
The explosive growth of Internet has raised interest in traffic analysis. Understanding what traffic...
Abstract: Quality of Service delivery in network services has been a mayor issue for both customers ...
Since its inception until today, the Internet has been in constant transformation. The analysis and ...
<p>For this thesis, a toolchain was designed that aimed to process network traffic to identify host ...
Abstract Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve p...
During my ten weeks at CERN, I have been working on two programs related to network monitoring. The ...
Traffic classification is an important aspect in network operation and management, but challenging f...
Networks are an integral part of society. Other than being the backbone of the internet, it is also ...
Abstract. Network engineers use different tools to manage and con-trol networks. While different too...
Communication networks provide the foundational services on which our modern economy depends. These ...
International audienceRecent development in smart devices has lead us to an explosion in data genera...
The main objective of the thesis is the development of a new software package for plotting of the ne...
Accurate per-application network traffic characterization is becoming in-creasingly difficult in the...
International audienceNowadays, Machine Learning (ML) tools are commonly used in every area of scien...
In order for businesses to maintain their productivity today, it iscrucial that they constantly moni...
The explosive growth of Internet has raised interest in traffic analysis. Understanding what traffic...
Abstract: Quality of Service delivery in network services has been a mayor issue for both customers ...
Since its inception until today, the Internet has been in constant transformation. The analysis and ...
<p>For this thesis, a toolchain was designed that aimed to process network traffic to identify host ...
Abstract Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve p...
During my ten weeks at CERN, I have been working on two programs related to network monitoring. The ...
Traffic classification is an important aspect in network operation and management, but challenging f...
Networks are an integral part of society. Other than being the backbone of the internet, it is also ...
Abstract. Network engineers use different tools to manage and con-trol networks. While different too...
Communication networks provide the foundational services on which our modern economy depends. These ...
International audienceRecent development in smart devices has lead us to an explosion in data genera...
The main objective of the thesis is the development of a new software package for plotting of the ne...
Accurate per-application network traffic characterization is becoming in-creasingly difficult in the...
International audienceNowadays, Machine Learning (ML) tools are commonly used in every area of scien...